Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Bind

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brushing
    -0.07
     executive
    -0.07
    ッと
    -0.07
    坋
    -0.07
     כ
    -0.06
     כש
    -0.06
    ชอบ
    -0.06
     Pharm
    -0.06
    כיכר
    -0.06
    :[↵
    -0.06
    POSITIVE LOGITS
    rede
    0.07
    stadt
    0.07
    Spo
    0.07
     Wyoming
    0.07
     Jackson
    0.07
    odon
    0.07
    fram
    0.07
     Katy
    0.07
    getBody
    0.06
     Appalach
    0.06
    Act Density 0.003%

    No Known Activations